EP1118956A3 - Object recognition method in images at pixel level - Google Patents

Object recognition method in images at pixel level Download PDF

Info

Publication number
EP1118956A3
EP1118956A3 EP00124269A EP00124269A EP1118956A3 EP 1118956 A3 EP1118956 A3 EP 1118956A3 EP 00124269 A EP00124269 A EP 00124269A EP 00124269 A EP00124269 A EP 00124269A EP 1118956 A3 EP1118956 A3 EP 1118956A3
Authority
EP
European Patent Office
Prior art keywords
images
classification
object class
relevant
pixel point
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
EP00124269A
Other languages
German (de)
French (fr)
Other versions
EP1118956A2 (en
Inventor
Christoph Stahl
Thomas Fechner
Oliver Rockinger
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Airbus Defence and Space GmbH
Original Assignee
EADS Deutschland GmbH
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by EADS Deutschland GmbH filed Critical EADS Deutschland GmbH
Publication of EP1118956A2 publication Critical patent/EP1118956A2/en
Publication of EP1118956A3 publication Critical patent/EP1118956A3/en
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G06F18/254—Fusion techniques of classification results, e.g. of results related to same input data

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Image Analysis (AREA)

Abstract

Die Erfindung betrifft ein Verfahren zur Erkennung von Objekten mindestens einer vorbestimmten Objektklasse auf der Pixelebene in Eingangsbildern, bei dem für jedes Eingangsbild (1) jeder Pixelpunkt in einer Grobklassifikation (10) aufgrund vorgegebener Kriterien als für die Objekterkennung relevant eingestuft wird und daraufhin ein auf die relevanten Pixelpunkte reduziertes Bild (11) gebildet wird, bei dem jedes reduzierte Bild (11) in einer Zerlegung (20) durch Filterung nach vorgegebenen Kriterien in zumindest zwei korrespondierende Filterbilder (21, 22, 23) zerlegt wird, wobei die für die Erkennung der Objekte relevanten Bildbestandteile und deren gegenseitigen Zuordnungen erhalten bleiben, bei dem in einem Klassifikationsschritt (30) aus den Filterbildern (21, 22, 23) mittels eines Ensembles von nach vorbestimmten Regeln arbeitenden Klassifikatoren Klassifikationsbilder (31a, 32a, 33a; 31b, 32b, 33b; 31c, 32c, 33c) mit Bewertungszahlen der Klassifikation für jede Objektklasse gebildet werden, bei dem in einer Fusion (40) die Klassifikationsbilder (31a, 32a, 33a; 31b, 32b, 33b; 31c, 32c, 33c) algorithmisch zu einer kombinierten Gesamtentscheidung (41a, 41 b, 41 c) für jede Objektklasse zusammengefaßt werden, bei dem in einer Erstellung des Entscheidungsergebnisses (50) für jeden Pixelpunkt des reduzierten Bildes (11) anhand der Fusionsbilder (41a, 41b, 41c) entschieden wird, ob und zu welcher Objektklasse der Pixelpunkt gehört.

Figure 00000001
The invention relates to a method for recognizing objects of at least one predetermined object class on the pixel level in input images, in which for each input image (1) each pixel point in a rough classification (10) is classified as relevant for object recognition on the basis of predetermined criteria and thereupon a relevant pixel points reduced image (11) is formed, in which each reduced image (11) is broken down in a decomposition (20) by filtering according to predetermined criteria into at least two corresponding filter images (21, 22, 23), the for the detection of the Objects relevant image components and their mutual assignments are preserved, in which in a classification step (30) from the filter images (21, 22, 23) using an ensemble of classifiers working according to predetermined rules, classification images (31a, 32a, 33a; 31b, 32b, 33b ; 31c, 32c, 33c) with evaluation numbers of the classification for each object class are formed, in which the classification images (31a, 32a, 33a; 31b, 32b, 33b; 31c, 32c, 33c) are algorithmically combined into a combined overall decision (41a, 41b, 41c) for each object class, in which the decision result (50) is created for each pixel point of the reduced image (11) on the basis of the fusion images (41a , 41b, 41c) it is decided whether and to which object class the pixel point belongs.
Figure 00000001
EP00124269A 1999-11-20 2000-11-13 Object recognition method in images at pixel level Ceased EP1118956A3 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE19955919 1999-11-20
DE19955919A DE19955919C1 (en) 1999-11-20 1999-11-20 Object recognition method for pixel images provides reduced image from input image which is divided by filtering into at least 2 filtered images each used for providing set of classification images

Publications (2)

Publication Number Publication Date
EP1118956A2 EP1118956A2 (en) 2001-07-25
EP1118956A3 true EP1118956A3 (en) 2003-05-07

Family

ID=7929768

Family Applications (1)

Application Number Title Priority Date Filing Date
EP00124269A Ceased EP1118956A3 (en) 1999-11-20 2000-11-13 Object recognition method in images at pixel level

Country Status (3)

Country Link
US (1) US6944342B1 (en)
EP (1) EP1118956A3 (en)
DE (1) DE19955919C1 (en)

Families Citing this family (25)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE19832974A1 (en) * 1998-07-22 2000-01-27 Siemens Ag Arrangement for generating virtual industrial system model compares system component information with real system image data to identify components in image data
US7099510B2 (en) * 2000-11-29 2006-08-29 Hewlett-Packard Development Company, L.P. Method and system for object detection in digital images
JP3817174B2 (en) * 2001-12-28 2006-08-30 矢崎総業株式会社 Vehicle image correction device and night driving visibility support device
DE10348109A1 (en) 2003-10-16 2005-05-19 Bayerische Motoren Werke Ag Method and device for visualizing a vehicle environment
US7606420B1 (en) * 2005-10-31 2009-10-20 Adobe Systems, Incorporated Method and apparatus for improving the speed of belief propagation
DE102006060612B4 (en) * 2006-12-21 2008-08-28 Eads Deutschland Gmbh Method for monitoring target objects and multispectral camera
WO2008110962A1 (en) * 2007-03-09 2008-09-18 Koninklijke Philips Electronics N.V. Visualization of parametric maps
DE102007021579A1 (en) * 2007-05-08 2008-11-13 Hella Kgaa Hueck & Co. Traffic sign i.e. circular traffic sign, classifying method, involves classifying object in dependence of classification process and/or classification result, by another different classification process for classification of traffic sign
DE102007021578A1 (en) * 2007-05-08 2008-11-13 Hella Kgaa Hueck & Co. Road sign classifying method, involves determining object, assigning image elements for each image of object, and accomplishing classification with help of determined image data, with which individual probability is determined
JP4586891B2 (en) * 2008-06-10 2010-11-24 コニカミノルタビジネステクノロジーズ株式会社 Color reduction method, color reduction processing apparatus, image forming apparatus, and computer program
DE102008038527A1 (en) 2008-08-20 2010-02-25 Eads Deutschland Gmbh Method for evaluating object elements in images of multispectral camera or synthetic aperture radar device, involves forming target object hypothesis
GB2471886A (en) * 2009-07-16 2011-01-19 Buhler Sortex Ltd Inspection apparatus
US8634653B1 (en) * 2010-06-02 2014-01-21 The Boeing Company Object identification system
DE102011010334B4 (en) 2011-02-04 2014-08-28 Eads Deutschland Gmbh Camera system and method for observing objects at a great distance, in particular for monitoring target objects at night, mist, dust or rain
JP5814700B2 (en) * 2011-08-25 2015-11-17 キヤノン株式会社 Image processing system and image processing method
DE102012002321B4 (en) 2012-02-06 2022-04-28 Airbus Defence and Space GmbH Method for recognizing a given pattern in an image data set
US9002095B2 (en) 2012-12-20 2015-04-07 Wal-Mart Stores, Inc. Faulty cart wheel detection
US9940545B2 (en) * 2013-09-20 2018-04-10 Change Healthcare Llc Method and apparatus for detecting anatomical elements
SG10201403293TA (en) * 2014-06-16 2016-01-28 Ats Group Ip Holdings Ltd Fusion-based object-recognition
JP6361387B2 (en) * 2014-09-05 2018-07-25 オムロン株式会社 Identification device and control method of identification device
DE102014113174A1 (en) * 2014-09-12 2016-03-17 Connaught Electronics Ltd. Method for determining characteristic pixels, driver assistance system and motor vehicle
US11461919B2 (en) * 2016-04-21 2022-10-04 Ramot At Tel Aviv University Ltd. Cascaded neural network
GB2549554A (en) * 2016-04-21 2017-10-25 Ramot At Tel-Aviv Univ Ltd Method and system for detecting an object in an image
CN108304775B (en) * 2017-12-26 2021-06-11 北京市商汤科技开发有限公司 Remote sensing image recognition method and device, storage medium and electronic equipment
CN110363224B (en) * 2019-06-19 2021-07-06 创新奇智(北京)科技有限公司 Object classification method and system based on image and electronic equipment

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5963653A (en) * 1997-06-19 1999-10-05 Raytheon Company Hierarchical information fusion object recognition system and method

Family Cites Families (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4881270A (en) * 1983-10-28 1989-11-14 The United States Of America As Represented By The Secretary Of The Navy Automatic classification of images
US5274714A (en) * 1990-06-04 1993-12-28 Neuristics, Inc. Method and apparatus for determining and organizing feature vectors for neural network recognition
DE4100500A1 (en) * 1991-01-10 1992-07-16 Bodenseewerk Geraetetech SIGNAL PROCESSING ARRANGEMENT FOR THE CLASSIFICATION OF OBJECTS BASED ON THE SIGNALS OF SENSORS
EP0602932B1 (en) * 1992-12-18 2001-03-14 Raytheon Company Improved pattern recognition system for sonar and other applications
US5835901A (en) * 1994-01-25 1998-11-10 Martin Marietta Corporation Perceptive system including a neural network
US5640468A (en) * 1994-04-28 1997-06-17 Hsu; Shin-Yi Method for identifying objects and features in an image
DE4438235B4 (en) * 1994-10-26 2005-04-07 LFK Lenkflugkörpersysteme GmbH Method for automatic detection of small moving objects in a natural environment, preferably a real-time image sequence
US5956427A (en) * 1995-06-15 1999-09-21 California Institute Of Technology DFT encoding of oriented filter responses for rotation invariance and orientation estimation in digitized images
JPH0991430A (en) * 1995-09-27 1997-04-04 Hitachi Ltd Pattern recognition device
US6038337A (en) * 1996-03-29 2000-03-14 Nec Research Institute, Inc. Method and apparatus for object recognition
US5937078A (en) * 1996-04-10 1999-08-10 The United States Of America As Represented By The Secretary Of The Navy Target detection method from partial image of target
JP2815045B2 (en) * 1996-12-16 1998-10-27 日本電気株式会社 Image feature extraction device, image feature analysis device, and image matching system
GB9808712D0 (en) * 1997-11-05 1998-06-24 British Aerospace Automatic target recognition apparatus and process
US6556708B1 (en) * 1998-02-06 2003-04-29 Compaq Computer Corporation Technique for classifying objects within an image
US6529614B1 (en) * 1998-08-05 2003-03-04 California Institute Of Technology Advanced miniature processing handware for ATR applications
US6263103B1 (en) * 1998-11-30 2001-07-17 Mitsubishi Electric Research Laboratories, Inc. Estimating scenes using statistical properties of images and scenes
US6042050A (en) * 1999-02-16 2000-03-28 The United States Of America As Represented By The Secretary Of The Army Synthetic discriminant function automatic target recognition system augmented by LADAR
US6393137B1 (en) * 1999-06-17 2002-05-21 Raytheon Company Multi-resolution object classification method employing kinematic features and system therefor

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5963653A (en) * 1997-06-19 1999-10-05 Raytheon Company Hierarchical information fusion object recognition system and method

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
CASASENT D ET AL: "DETECTION FILTERS AND ALGORITHM FUSION FOR ATR", IEEE TRANSACTIONS ON IMAGE PROCESSING, IEEE INC. NEW YORK, US, vol. 6, no. 1, 1997, pages 114 - 125, XP000642456, ISSN: 1057-7149 *
LUO R C ET AL: "A tutorial on multisensor integration and fusion", SIGNAL PROCESSING AND SYSTEM CONTROL, FACTORY AUTOMATION. PACIFIC GROVE, NOV. 27 - 30, 1990, PROCEEDINGS OF THE ANNUAL CONFERENCE OF THE INDUSTRIAL ELECTRONICS SOCIETY. (IECON), NEW YORK, IEEE, US, vol. 1 CONF. 16, 27 November 1990 (1990-11-27), pages 707 - 722, XP010038257, ISBN: 0-87942-600-4 *
WANG L-C ET AL: "AUTOMATIC TARGET RECOGNITION USING A FEATURE-DECOMPOSITION AND DATA-DECOMPOSITION MODULAR NEURAL NETWORK", IEEE TRANSACTIONS ON IMAGE PROCESSING, IEEE INC. NEW YORK, US, vol. 7, no. 8, 1 August 1998 (1998-08-01), pages 1113 - 1121, XP000768985, ISSN: 1057-7149 *

Also Published As

Publication number Publication date
EP1118956A2 (en) 2001-07-25
DE19955919C1 (en) 2001-05-31
US6944342B1 (en) 2005-09-13

Similar Documents

Publication Publication Date Title
EP1118956A3 (en) Object recognition method in images at pixel level
DE102018116111B4 (en) A unified deep convolutional neural network for free space estimation, object recognition estimation, and object pose estimation
Pal et al. Performance of an off-line signature verification method based on texture features on a large indic-script signature dataset
DE102004033156B4 (en) Motion detection using multi-resolution image processing
DE102017220307B4 (en) Device and method for recognizing traffic signs
US6021220A (en) System and method for pattern recognition
EP2187351B1 (en) Device and method for detecting objects
CN101087365B (en) A method for filtering image mixed noise
EP1274047A3 (en) Multimodal biometrics
EP0821346A3 (en) Method for speaker verification by a computer by means of at least one speech signal spoken in by a speaker
DE102006012914A1 (en) System and method for determining the distance to a preceding vehicle
DE102006057552A1 (en) System and method for measuring the distance of a preceding vehicle
DE19636949A1 (en) Method for the detection of edges in an image signal
EP1306813A3 (en) Method and device for automated calculation of postage charges
DE102015207903A1 (en) Apparatus and method for detecting a bar-type traffic sign in a traffic sign recognition system
DE69728469T2 (en) Apparatus and method for determining the character line using simplified projection information; Character recognition device and method
DE102005025220A1 (en) Apparatus, method and program for removing pores
US7113636B2 (en) Method and computer program product for generating training data for a new class in a pattern recognition classifier
EP1989662B1 (en) Method for identifying objects, and object identification system
DE112019007857T5 (en) MOTION ANALYSIS SYSTEM AND MOTION ANALYSIS PROGRAM
WO2009015655A2 (en) Method and apparatus for automatic pattern recognition
DE10234086B4 (en) Method for signal evaluation of an electronic image sensor in the pattern recognition of image contents of a test specimen
CN112580705B (en) Hyperspectral classification method based on deep feed-forward network
Gary et al. A fuzzy-attributed graph approach to handwritten character recognition
Ghazali et al. Machine vision system for automatic weeding strategy in oil palm plantation using image filtering technique

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

AK Designated contracting states

Kind code of ref document: A2

Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LI LU MC NL PT SE TR

AX Request for extension of the european patent

Free format text: AL;LT;LV;MK;RO;SI

PUAL Search report despatched

Free format text: ORIGINAL CODE: 0009013

RAP1 Party data changed (applicant data changed or rights of an application transferred)

Owner name: EADS DEUTSCHLAND GMBH

AK Designated contracting states

Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LI LU MC NL PT SE TR

AX Request for extension of the european patent

Extension state: AL LT LV MK RO SI

17P Request for examination filed

Effective date: 20030523

AKX Designation fees paid

Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LI LU MC NL PT SE TR

17Q First examination report despatched

Effective date: 20080313

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION HAS BEEN REFUSED

18R Application refused

Effective date: 20110509